Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 10-RES-JB
    6. 1212
    Prev
    Next
    INDEX
    Explanations

    phrases related to "drop" in various contexts, particularly in terms of measurement or reduction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.21
    1.2%
    755
    +0.11
    0.7%
    1233
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    755
    +0.21
    0.03
    1895
    +0.11
    0.03
    1233
    +0.11
    0.03
    Negative Logits
    <bos>
    -2.67
    public
    -0.71
    real
    -0.66
    com
    -0.65
    char
    -0.64
    setViewName
    -0.64
    ҡ
    -0.63
     Commission
    -0.63
    stereotype
    -0.63
    int
    -0.62
    POSITIVE LOGITS
     apprehen
    2.04
     emphat
    1.95
     reluct
    1.93
     ftu
    1.91
     maneu
    1.90
     thut
    1.89
     fta
    1.89
     disagre
    1.85
     accla
    1.84
     Juf
    1.81
    Activations Density 0.046%

    No Known Activations